LotPilot
Turn property documents into structured data.
2026
Development recorded in the project repository. Earlier work may predate this history; this is not a confirmed launch date.AI & integrations
Inside LotPilot
The live LotPilot application entry point.
The problem
Property-auction work involves finding opportunities, building auctions and lots, tracking apartments and keeping source material understandable as new catalogues, addenda and notes arrive. Teams need one dependable operational record instead of documents and manually maintained lists.
Much of the input is unstructured, but extracting text is only part of the problem: new material may correct an existing lot, every change needs review and organisations must never see one another's records.
The solution
LotPilot is the shared auction workspace for auctions, lots, apartments, documents and team roles. It turns PDFs, photographs, links and free text into structured candidate records and presents proposed additions and corrections for an operator to review before anything changes.
Repeated imports reconcile against existing auctions and lot numbers rather than duplicating them. Source references preserve provenance, and organisation-scoped permissions distinguish editors from viewers across the full platform and its MCP integration.
The decisions behind it
- Extraction before commitment
- AI prepares a candidate result. Validation and a human review step sit between that result and the auction database.
- Re-import means reconcile
- The same document may be processed more than once. Stable matching rules decide whether a row creates a lot or updates one.
- Auction, lot and apartment management
- AI extraction with review before saving
- Organisation-scoped MCP integration